rams

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues detected in the skill instructions or metadata. The skill is limited to performing static analysis and suggesting code improvements for accessibility.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing external code content.\n
  • Ingestion points: The skill processes UI component files provided via the $ARGUMENTS variable or manual user selection.\n
  • Boundary markers: Absent; the instructions do not define specific delimiters or instructions to prevent the agent from obeying commands embedded within the code files being reviewed.\n
  • Capability inventory: The skill performs file reads for analysis and offers to write or modify code to apply accessibility fixes.\n
  • Sanitization: No input sanitization or validation of the code-under-review is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 04:45 AM